Audio-Visual Data: Compression and Indexing

                           Abdou Youssef
                  The George Washington University

                              ABSTRACT

 
Many current and near-future applications involve massive amounts of 
audio and/or visual data.  Those include medicine, space related 
applications, fingerprint processing, digital libararies, and video 
on demands, to name a few.  The storage and transmission of the 
staggering amounts of audio-visual data require compression.  Also, 
querying and accessing large repositories of audio-visual data 
require sophisticated indexing methods, radically different from 
text indexing techniques.  This talk will cover principles and 
techniques for compression, and show how those techniques are 
applied to indexing.  The talk will also touch upon a hierarchy of 
indexing schemes that need to be studied and developed to make 
audio-image-video database search a useful tool at many levels.  

--------------------------------------------------------------------
 
 Prof.  Abdou Youssef received the B.S.  degree in Mathematics 
from The Lebanese University in 1981, the M.A.  and Ph.D degrees in 
Computer Science from Princeton University, in 1985 and 1988, 
respectively.  He has been with the Department of Electrical 
Engineering and Computer Science at The George Washington 
University, Washington DC, since 1987, serving as Assistant 
Professor from 1987 to 1993, and Associate Professor starting from 
1993.  He has published numerous papers in the areas of parallel 
processing, computer architecture, and recently in image/signal 
processing, data compression, and multimedia databases.  He also 
co-edited a book titled ``Interconnection Networks for 
High-Performance Parallel Computers'', published by the IEEE 
Computer Society Press in 1994.  His research interests include data 
compression, image and video processing, error recovery and fault 
tolerance, algorithms, parallel processing and computer 
architecture.  Professor Youssef is a senior member of IEEE and a 
member of ACM.